From:	stl137 AT aol DOT com (S. T. L.)
Newsgroups:	comp.os.msdos.djgpp
Subject:	Re: Voodoo optimization?
Lines:	18
NNTP-Posting-Host:	ladder07.news.aol.com
X-Admin:	news AT aol DOT com
Date:	07 Jul 2000 03:28:32 GMT
References:	<Pine DOT LNX DOT 4 DOT 21 DOT 0007061935210 DOT 1891-100000 AT roadrunner DOT grendel DOT net>
Organization:	AOL http://www.aol.com
Message-ID:	<20000706232832.25697.00001192@ng-bh1.aol.com>
To:	djgpp AT delorie DOT com
DJ-Gateway:	from newsgroup comp.os.msdos.djgpp
Reply-To:	djgpp AT delorie DOT com

<<Did you try -O3..what effect did that have, sometimes it causes the 
compiler to output code that overflows the cache etc..which can make it
slower than -O2.>>

Tried -O3... no effect.  :-<

<<Sometimes(often?), unroling loops,and inlining functions can be slower on
586,686 architectures due to the cache overflows etc...>>

Apparently, inlining functions doesn't have an effect on the BladeEnc code,
while unrolling loops greatly benefits it.

Thanks for your time!

-*---*-------
S.T.L.  My Quotes Page * http://quote.cjb.net * leads to my NEW site.
Pages up: 419 Quotes, 52 reviews of 169 science books, and a review of
the Foundation series. Newest Page: S.T.L.'s Files for Download!

- Raw text -